The commit code already contains code for validating UTF-8, but it does not
check for invalid values, such as guaranteed non-characters and surrogates.  Fix
this by explicitly checking for and rejecting such characters.

Signed-off-by: brian m. carlson <sand...@crustytoothpaste.net>
---
 commit.c                  | 18 +++++++++++++++---
 t/t3900-i18n-commit.sh    |  9 +++++++++
 t/t3900/UTF-8-invalid.txt |  3 +++
 3 files changed, 27 insertions(+), 3 deletions(-)
 create mode 100644 t/t3900/UTF-8-invalid.txt

diff --git a/commit.c b/commit.c
index 888e02a..2280413 100644
--- a/commit.c
+++ b/commit.c
@@ -1244,6 +1244,7 @@ static int find_invalid_utf8(const char *buf, int len)
        while (len) {
                unsigned char c = *buf++;
                int bytes, bad_offset;
+               unsigned int codepoint;
 
                len--;
                offset++;
@@ -1264,24 +1265,35 @@ static int find_invalid_utf8(const char *buf, int len)
                        bytes++;
                }
 
-               /* Must be between 1 and 5 more bytes */
-               if (bytes < 1 || bytes > 5)
+               /* Must be between 1 and 3 more bytes */
+               if (bytes < 1 || bytes > 3)
                        return bad_offset;
 
                /* Do we *have* that many bytes? */
                if (len < bytes)
                        return bad_offset;
 
+               /* Place the encoded bits at the bottom of the value. */
+               codepoint = (c & 0x7f) >> bytes;
+
                offset += bytes;
                len -= bytes;
 
                /* And verify that they are good continuation bytes */
                do {
+                       codepoint <<= 6;
+                       codepoint |= *buf & 0x3f;
                        if ((*buf++ & 0xc0) != 0x80)
                                return bad_offset;
                } while (--bytes);
 
-               /* We could/should check the value and length here too */
+               /* Check the value here */
+               if (codepoint >= 0xd800 && codepoint <= 0xdfff)
+                       return bad_offset;
+               if (codepoint > 0x10ffff)
+                       return bad_offset;
+               if ((codepoint & 0x1ffffe) == 0xfffe)
+                       return bad_offset;
        }
        return -1;
 }
diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh
index 37ddabb..16ed707 100755
--- a/t/t3900-i18n-commit.sh
+++ b/t/t3900-i18n-commit.sh
@@ -39,6 +39,15 @@ test_expect_failure 'UTF-16 refused because of NULs' '
        git commit -a -F "$TEST_DIRECTORY"/t3900/UTF-16.txt
 '
 
+test_expect_success 'UTF-8 invalid characters refused' '
+       rm -f "$HOME/stderr" &&
+       echo "UTF-8 characters" >F &&
+       git commit -a -F "$TEST_DIRECTORY"/t3900/UTF-8-invalid.txt \
+               2>"$HOME"/stderr &&
+       grep "did not conform" "$HOME"/stderr
+'
+
+rm -f "$HOME/stderr"
 
 for H in ISO8859-1 eucJP ISO-2022-JP
 do
diff --git a/t/t3900/UTF-8-invalid.txt b/t/t3900/UTF-8-invalid.txt
new file mode 100644
index 0000000..343684d
--- /dev/null
+++ b/t/t3900/UTF-8-invalid.txt
@@ -0,0 +1,3 @@
+Commit message
+
+Invalid surrogate:???
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to